video-color-grading

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill accepts arbitrary public video URLs via the "video_urls" parameter in SKILL.md (see Quick Start and numerous examples like "video_urls": ["https://example.com/reference-clip.mp4"]), clearly ingesting untrusted third-party media that the agent reads and uses (e.g., reference-clip matching) to determine processing and follow-up actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 07:58 AM